• ADDANKI SHIVA SAI
• MADAS BHARADWAJ
• BAIRI SIDDHARTHA
• THOTA RAMAKRISHNA

The rapid advancements in Convolutional Neural Network (CNN) methods have significantly propelled the field of image classification and identification tasks, overshadowing the conventional Vision Transformer (ViT) approaches. Despite recent studies highlighting ViT's superiority in image classification, this research introduces an enhanced CNN-based model tailored specifically for pest recognition, segmentation, and classification tasks. By leveraging a double-layer CNN encoder, our novel approach adeptly incorporates two-branch segment representations, effectively managing token chunks of varying sizes and computational complexities. Furthermore, various attention mechanisms are integrated to enhance the overall image comprehension. Through extensive experimentation utilizing publicly available pest databases affecting peanut and other crops, our proposed CNN model exhibits distinctive characteristics and outperforms state-of-the-art algorithms in pest image prediction, achieving an impressive accuracy rate of 99.25%.

Big Data Analytics Framework , Perinatal Mental Health , Machine Learning Techniques , Depression and Anxiety Disorders , Feature Selection , Hybrid Machine Learning , Scalable Big Data Platform , Rapid Disease Diagnosis

"Pest Detection and Classification in Peanut Crops Using CNN, and EViTA Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.a316-a320, May-2024, Available :http://www.jetir.org/papers/JETIR2405038.pdf

"Pest Detection and Classification in Peanut Crops Using CNN, and EViTA Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppa316-a320, May-2024, Available at : http://www.jetir.org/papers/JETIR2405038.pdf